Loading...
Loading...
Found 5,519 Skills
Sharpen, refine, and optimize AI agent skills through real usage — learn from mistakes, review quality, and improve over time. Observes skill execution in the current conversation, analyzes three sources (conversation history, file diffs, user feedback), and proposes concrete improvements to the target skill's SKILL.md. Works with Claude Code and any SKILL.md-based agent framework. Use after executing any skill: `/skill-sharpen [name]` for a specific skill, or `/skill-sharpen` to auto-detect the last used. Three modes: interactive (propose one by one), observe-only (dump to LESSONS.md), review (process pending lessons).
Use when designing, planning, implementing, or reviewing any non-trivial change — enforces small, focused modules so any change fits in context without compaction
Use when the user wants to deploy and run a prepared AWS FIS experiment. Triggers on "execute FIS experiment", "run FIS experiment", "start chaos experiment", "deploy FIS template", "启动 FIS 实验", "运行混沌实验", "执行故障注入实验", "deploy and run the experiment in [directory]". Expects a prepared experiment directory (from aws-fis-experiment-prepare or manually created) containing experiment-template.json, iam-policy.json, cfn-template.yaml, and alarm configs. Deploys resources via CLI or CloudFormation, starts the experiment with strict user confirmation, monitors progress, and generates results report.
Guide for implementing the Syncfusion WinUI Shimmer control to display loading placeholders and skeleton screens. Use this skill when implementing shimmer effects, skeleton screens, content loading animations, or loading placeholders during data fetching in WinUI applications. Essential for enhancing perceived performance during async operations, list loading, profile loading, article loading, or any content loading scenario requiring visual feedback.
Use before claiming any task is complete, any feature works, or any bug is fixed - enforces fresh verification evidence through a 5-step HARD-GATE protocol that prevents false completion claims
Use when writing any new code, adding features, or fixing bugs that require code changes. Enforces strict RED-GREEN-REFACTOR cycle with no production code without a failing test first. Triggers: new feature implementation, bug fix, refactoring existing code, adding behavior to existing modules.
Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes.
Manage the full lifecycle of Alibaba Cloud E-MapReduce (EMR) ECS clusters—creation, scaling, renewal, and status queries. Use this Skill when users want to set up big data clusters, view cluster status, add nodes, release nodes, configure auto-scaling, check cluster and node states, or diagnose creation failures. Also applicable for scenarios like "create a Hadoop cluster", "data lake cluster", "running out of resources", "check my cluster", "renew", etc. NOTE: This Skill does NOT support cluster deletion, release, or termination under any circumstances. Any request to delete or terminate a cluster will be refused and redirected to the EMR console.
Implement Syncfusion ProgressBarAdv control in Windows Forms for displaying operation progress with customizable text formats. Use when creating progress indicators, loading bars, or percentage displays with Percentage, Value, or Custom text formats. Covers orientation (horizontal/vertical), themes, progress tracking, and progress events for file operations, installations, or download indicators.
Security Check - Security review for skills before installation. Triggers: Before installing new skills, regular review of installed skills, or when security issues with a skill are suspected. Security Checks: - Dangerous Commands: rm -rf, sudo, curl|bash, etc. - Network Requests: Potential data leakage risks - File Writes: Writing to sensitive locations - Credentials: Risk of API key/password leakage - Resource Exhaustion: Infinite loops - Privilege Escalation: Privilege escalation attempts - External Dependencies: Suspicious dependencies Commands: - /安检 <skill-path> - Review skill security - /安检 scan <path> - Deep scan - /安检 list - List risks of installed skills - /安检 fix <skill> - Fix security issues - /security <skill-path> - English command Actions: - Auto-fix: Remove or replace dangerous code - Disable: Disable dangerous features - User Confirm: User chooses whether to proceed - Block: Block installation for severe risks Capabilities: Static code analysis, dangerous pattern recognition, risk assessment, auto-fix, user interactive decision making.
Design and optimize CRM systems and client lifecycle workflows for advisory firms, covering segmentation, household management, service tiers, and retention analytics. Use when the user asks about client segmentation models, building household structures, defining service tier SLAs, scheduling reviews, tracking lifecycle stages from prospect through estate, identifying at-risk clients, analyzing wallet share, consolidating held-away assets, or evaluating CRM platforms. Also trigger when users mention 'client segmentation', 'retention risk', 'at-risk clients', 'household linking', 'multi-generational', 'service tiers', 'Redtail', 'Wealthbox', 'Salesforce for advisors', 'referral tracking', or 'contact gap'.
Outscraper platform help — data extraction platform that scrapes Google Maps, reviews, and 50+ sources plus an instant Business Catalog database. Use when scraping Google Maps businesses or reviews, extracting emails/contacts from websites, enriching company data, validating emails, scraping Amazon or review platforms, or working with the Outscraper API. Do NOT use for general prospect list strategy (use /sales-prospect-list), cross-platform enrichment strategy (use /sales-enrich), or email deliverability strategy (use /sales-deliverability).